{"id":"https://openalex.org/W4385767293","doi":"https://doi.org/10.24963/ijcai.2023/24","title":"Deep Hierarchical Communication Graph in Multi-Agent Reinforcement Learning","display_name":"Deep Hierarchical Communication Graph in Multi-Agent Reinforcement Learning","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385767293","doi":"https://doi.org/10.24963/ijcai.2023/24"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/24","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/24","pdf_url":"https://www.ijcai.org/proceedings/2023/0024.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0024.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054589937","display_name":"Zeyang Liu","orcid":"https://orcid.org/0000-0002-3553-3793"},"institutions":[{"id":"https://openalex.org/I4210105595","display_name":"Institute of Art","ror":"https://ror.org/017fyx225","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210105595","https://openalex.org/I99542240"]},{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN","PL"],"is_corresponding":false,"raw_author_name":"Zeyang Liu","raw_affiliation_strings":["National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University","institution_ids":["https://openalex.org/I4210105595","https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101790448","display_name":"Lipeng Wan","orcid":"https://orcid.org/0000-0002-8310-0837"},"institutions":[{"id":"https://openalex.org/I4210105595","display_name":"Institute of Art","ror":"https://ror.org/017fyx225","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210105595","https://openalex.org/I99542240"]},{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN","PL"],"is_corresponding":false,"raw_author_name":"Lipeng Wan","raw_affiliation_strings":["National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University","institution_ids":["https://openalex.org/I4210105595","https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042809978","display_name":"Xue Sui","orcid":"https://orcid.org/0000-0002-4746-764X"},"institutions":[{"id":"https://openalex.org/I4210105595","display_name":"Institute of Art","ror":"https://ror.org/017fyx225","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210105595","https://openalex.org/I99542240"]},{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN","PL"],"is_corresponding":false,"raw_author_name":"Xue Sui","raw_affiliation_strings":["National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University","institution_ids":["https://openalex.org/I4210105595","https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108484845","display_name":"Zhuoran Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210105595","display_name":"Institute of Art","ror":"https://ror.org/017fyx225","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210105595","https://openalex.org/I99542240"]},{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN","PL"],"is_corresponding":false,"raw_author_name":"Zhuoran Chen","raw_affiliation_strings":["National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University","institution_ids":["https://openalex.org/I4210105595","https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088277258","display_name":"Kewu Sun","orcid":"https://orcid.org/0000-0002-1770-304X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kewu Sun","raw_affiliation_strings":["Intelligent Science and Technology Academy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Science and Technology Academy","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006277484","display_name":"Xuguang Lan","orcid":"https://orcid.org/0000-0002-3422-944X"},"institutions":[{"id":"https://openalex.org/I4210105595","display_name":"Institute of Art","ror":"https://ror.org/017fyx225","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210105595","https://openalex.org/I99542240"]},{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN","PL"],"is_corresponding":false,"raw_author_name":"Xuguang Lan","raw_affiliation_strings":["National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University","institution_ids":["https://openalex.org/I4210105595","https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"208","last_page":"216"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.779044508934021},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.7286787033081055},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6882932782173157},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5449569821357727},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.5434823036193848},{"id":"https://openalex.org/keywords/directed-acyclic-graph","display_name":"Directed acyclic graph","score":0.4384421110153198},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3836967945098877},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3509577512741089},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1358320713043213},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13053607940673828}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.779044508934021},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.7286787033081055},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6882932782173157},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5449569821357727},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5434823036193848},{"id":"https://openalex.org/C74197172","wikidata":"https://www.wikidata.org/wiki/Q1195339","display_name":"Directed acyclic graph","level":2,"score":0.4384421110153198},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3836967945098877},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3509577512741089},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1358320713043213},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13053607940673828}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/24","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/24","pdf_url":"https://www.ijcai.org/proceedings/2023/0024.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/24","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/24","pdf_url":"https://www.ijcai.org/proceedings/2023/0024.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17","score":0.5}],"awards":[{"id":"https://openalex.org/G1273828380","display_name":null,"funder_award_id":"xtr072022001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2993312730","display_name":null,"funder_award_id":"61973246","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3833898155","display_name":null,"funder_award_id":"62088102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7025311388","display_name":null,"funder_award_id":"No. 62088102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8180423952","display_name":null,"funder_award_id":"62125305","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8808651841","display_name":null,"funder_award_id":"xtr072022001","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385767293.pdf"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1983289383","https://openalex.org/W2118318536","https://openalex.org/W2129523668","https://openalex.org/W2736601468","https://openalex.org/W2747213132","https://openalex.org/W2803155336","https://openalex.org/W2803728337","https://openalex.org/W2804327232","https://openalex.org/W2949794851","https://openalex.org/W2949963774","https://openalex.org/W2952369555","https://openalex.org/W2963864421","https://openalex.org/W2964338167","https://openalex.org/W2971727319","https://openalex.org/W2978236943","https://openalex.org/W2979284752","https://openalex.org/W2981038142","https://openalex.org/W2994864869","https://openalex.org/W2995061808","https://openalex.org/W2998367975","https://openalex.org/W3036295212","https://openalex.org/W3046288222","https://openalex.org/W3091492359","https://openalex.org/W3105017587","https://openalex.org/W3128366769","https://openalex.org/W3168414797","https://openalex.org/W3170888258","https://openalex.org/W3200561352","https://openalex.org/W4225602276","https://openalex.org/W4281622133","https://openalex.org/W4283032009","https://openalex.org/W4283789768","https://openalex.org/W4286748781","https://openalex.org/W4287755265","https://openalex.org/W4288594419","https://openalex.org/W4289363497","https://openalex.org/W4293586424","https://openalex.org/W4295598622"],"related_works":["https://openalex.org/W2487162673","https://openalex.org/W2793211469","https://openalex.org/W2949152769","https://openalex.org/W4372354731","https://openalex.org/W2942366970","https://openalex.org/W2807634898","https://openalex.org/W1692008701","https://openalex.org/W2597588799","https://openalex.org/W4360593462","https://openalex.org/W2562400057"],"abstract_inverted_index":{"Sharing":[0],"intentions":[1],"is":[2,29,88],"crucial":[3],"for":[4,32,134],"efficient":[5],"cooperation":[6],"in":[7,41,95,103,119,160],"communication-enabled":[8],"multi-agent":[9,191],"reinforcement":[10],"learning.":[11],"Recent":[12],"work":[13],"applies":[14],"static":[15,27],"or":[16],"undirected":[17,43],"graphs":[18,79],"to":[19,61,172],"determine":[20],"the":[21,26,37,42,63,82,85,101,104,117,120,142,145,157,168],"order":[22],"of":[23,84,124,144],"interaction.":[24],"However,":[25],"graph":[28,44,118],"not":[30],"general":[31],"complex":[33],"cooperative":[34,190],"tasks,":[35,192],"and":[36,93,114,137,151,164,176,198],"parallel":[38],"message-passing":[39],"update":[40],"with":[45],"cycles":[46,102],"cannot":[47],"guarantee":[48],"convergence.":[49,139],"To":[50,99,140],"solve":[51],"this":[52],"problem,":[53],"we":[54,106,148],"propose":[55,149],"Deep":[56],"Hierarchical":[57],"Communication":[58],"Graph":[59],"(DHCG)":[60],"learn":[62],"dependency":[64],"relationships":[65,73],"between":[66],"agents":[67],"based":[68],"on":[69],"their":[70],"messages.":[71],"The":[72],"are":[74],"formulated":[75],"as":[76,90,111],"directed":[77],"acyclic":[78],"(DAGs),":[80],"where":[81],"selection":[83],"proper":[86],"topology":[87],"viewed":[89],"an":[91,96,108,161],"action":[92],"trained":[94],"end-to-end":[97],"fashion.":[98],"eliminate":[100],"graph,":[105],"apply":[107],"acyclicity":[109],"constraint":[110],"intrinsic":[112],"rewards":[113],"then":[115],"project":[116],"admissible":[121],"solution":[122],"set":[123],"DAGs.":[125],"As":[126],"a":[127],"result,":[128],"DHCG":[129,155,166],"removes":[130],"redundant":[131],"communication":[132],"edges":[133],"cost":[135],"improvement":[136],"guarantees":[138],"show":[141,182],"effectiveness":[143],"learned":[146],"graphs,":[147],"policy-based":[150],"value-based":[152,165],"DHCG.":[153],"Policy-based":[154],"factorizes":[156,167],"joint":[158,169],"policy":[159],"auto-regressive":[162],"manner,":[163],"value":[170,174],"function":[171],"individual":[173],"functions":[175],"pairwise":[177],"payoff":[178],"functions.":[179],"Empirical":[180],"results":[181],"that":[183],"our":[184],"method":[185],"improves":[186],"performance":[187],"across":[188],"various":[189],"including":[193],"Predator-Prey,":[194],"Multi-Agent":[195,200],"Coordination":[196],"Challenge,":[197],"StarCraft":[199],"Challenge.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}